Machine Learning / Cloud Computing
3,984 words
Machine Learning on Cloud: Fraud Detection Model Design, Training and Evaluation
This postgraduate group project focuses on the design, development and critical evaluation of a cloud-based machine learning solution for financial fraud detection. The scenario involves a financial services organisation seeking to detect fraudulent transactions in order to reduce financial losses and improve customer security. Students are required to analyse an appropriate dataset, develop a machine learning solution, evaluate its effectiveness and critically consider the suitability of cloud technologies for deployment. The project begins with a cloud feasibility study, requiring critical comparison of at least two major machine learning platforms such as Microsoft Azure, Amazon Web Services and Google Cloud Platform. Evaluation criteria include performance, scalability, cost, compliance, integration and vendor lock-in, followed by a justified recommendation. Students then conduct exploratory data analysis to identify patterns, anomalies and correlations using appropriate visualisations such as heatmaps, histograms and boxplots. A substantial component addresses data preprocessing and class imbalance. Students are expected to clean and transform the data, apply scaling and encoding, perform feature engineering and investigate approaches such as SMOTE, undersampling and cost-sensitive learning. Each preprocessing choice must be justified in terms of its potential impact on model performance. Students must select and train at least two machine learning models, with suggested approaches including Logistic Regression, Random Forest, XGBoost and Neural Networks. Model development incorporates cross-validation and hyperparameter tuning. Evaluation uses fraud-relevant measures including Precision, Recall, F1 score, AUC and precision-recall curves, supported by confusion matrices, ROC curves and feature-importance visualisations. The project concludes with critical consideration of professional and ethical issues in cloud-based AI, including bias, fairness, transparency, data privacy and sustainability. The overall assessment therefore integrates cloud-platform evaluation, machine learning development, imbalanced classification, model evaluation and responsible AI practice. Overview word count: approximately 340 words.
Read Model Answer →
Cloud Computing / Big Data Technologies / Cyber Security
2,500 words
Cloud and Big Data Security Application: Design, Implementation and Evaluation
This assessment for the Cloud and Big Data Technologies module requires students to design, implement and evaluate an individual cloud-based or distributed data application. The project focuses on practical solutions involving the complex transformation, processing, storage and security of big data within cloud environments. Students are expected to demonstrate how distributed data can be organised in the cloud, how data pipelines can be used to access or process distributed databases, and how appropriate security controls can be incorporated into the resulting architecture. Students have considerable freedom when selecting their application. Suggested project directions include developing a data-science solution using SQL or MongoDB with cloud storage and an appropriate security policy; implementing privacy-preserving distributed processing using techniques such as Differential Privacy; creating multi-party authentication and group-based access-control mechanisms; or designing Multi-Level Security, Attribute-Based Encryption or Role-Based Access Control solutions. Projects may also examine distributed or cloud applications using security protocols such as SSH, SSL or IPsec. Creativity and originality are explicitly encouraged. The written component is a Design and Implementation Document of no more than approximately 2,500 words. It should present the project aims and objectives, application concept, cloud and security technologies, functional and security requirements, architecture and design decisions, protocols, access-control mechanisms, implementation process, achievements, problems encountered and overall evaluation. Relevant diagrams, such as interaction or sequence diagrams, may be used to explain system behaviour and architecture. The assessment also requires submission of the functioning Cloud and Big Data Security application and a 7-minute highlight demonstration video. The video should demonstrate the application's major features, implementation details, security functionality and, where appropriate, attack scenarios. Assessment places strong emphasis on the quality of the design and implementation documentation, originality, use of advanced features, and the overall effort and technical quality of the completed application. Students are therefore expected to demonstrate independent development rather than simply reproduce an existing tutorial.
Read Model Answer →